Application of Item Response Theory in the Development and Validation of Multiple Choice Test in Mathematics
DOI:
https://doi.org/10.66545/27ept985Keywords:
Mathematics and Standard Error of Measurement., Multiple-Choice Test, Item Response Theory (IRT)Abstract
The study applied three-parameter logistic model (3PLM) of IRT in the development and validation of Mathematics Multiple-Choice Test items. Two research questions were raised along with two hypotheses postulated to guide the conduct of the study. The study adopted instrumentation research design which involved the development of instrument for educational purpose. This study was conducted in Owerri Education Zone of Imo State. A sample of 1080 SS2 students was drawn from a population of 6,823 students that made up of all the SS2 students using simple random sampling techniques. The instrument for data collection for this study is Mathematics Multiple – Choice Test (MMT) developed by the researchers. The reliability coefficient 0.97 for the instrument was computed using Kuder Richardson formula twenty (KR ). Research questions were answered using standard errors of estimation and Chi- 20 square goodness of fit. While hypotheses were tested using p-value, z-test of significant of proportion and z-value for testing the fit of the items to the three-parameter logistic model (3PLM). Some of the findings of the study revealed that forty-seven out of the fifty items have Standard Errors of Estimation (SEE) of discrimination parameters below 0.1, while only three has SEEs of a above the criterion of 0.1. Forty-four items have SEEs of difficulty parameters that are below 0.1, while only six have SEEs of b above 0.1. The study therefore, recommends that secondary school Mathematics teachers should confidently use the items of the test in assessing their students since the items have good standard errors of estimation for the three items parameters.
References
Abonyi, O.S. (2011). Instrument in behavioural research: Apractical approach.Timex publishing company.
Adedoyin, O. O. (2010). Investigating the invariance of Person parameter estimates based on classical test and item response theories. International Journal Education Science, 2(2), 107 – 113.
Ajuonuma, J. (2016). Construction and administration of teacher – made tests and standardized tests inOgomaka, P.M.C, Ekwonye, E.C, Ukozor, F. I, and Onah, F. E, (Eds) measurement and evaluation: A comprehensive text for students and teachers. Flash point publishers. Pp218 – 255
Ali, A. (2014). Conducting research in education and the social sciences.Tashiwa Networks Ltd.
Allen, M.J. & Yen, W.M, (2002). Introduction to measurement theory. Long Grove, IL: Waveland press.
Anene G.U, & Ndubuisi O.G, (2015). Test development process. In B.G. Nworgu (Ed) Educational measurement and evaluation: Theory and practice (pp 110 – 122). University trust publishers.
Crocker, L, & Algina, J. (2018). Introduction to classical and modern test theory. Fort Worth: Harcourt Brace Jovanovich.
Ejimaji, E.U., & Ojedapo, D.O., (2017). Fundamentals of educationa measurement and evaluation. Jef-printing and publishing Co.
Ekwonye, E.C. (2015). Construction and administration of teacher made and standardized test. In Ekwonye, E.C, Uzoma, P.N, Offor, L, &Eguzo, G.O. Introduction to testing and continuous assessment. (pp108 – 124). Uzopietro Publishers Company
Ekwonye, E.C.& Eguzo G.O. (2011). Basic test theory in measurement and evaluation. Joemankpa publishers.
Ercikan, K. & Koh, K. (2015). Construct comparability of the English and French versions of TIMSS.International journal of testing (5), 23-35.
Ernest, P, (2015). International journal of education in Mathematics, science and technology. 3(3), 187 – 192.
Henard, D.H, (2000). Item response theory in reading and understanding more multivariate statistics, vol. II, Larry Grimm and Paul Yarnold, (Eds). American Psychological Association 67-97.
Iweka, F. (2017). Application of one parameter latent trait theory in the construct test items validity of Mathematics.Internation Journal of Interdisplinary Research Methods. 4(3), 11 – 22.
Jayanthi, E.C. (2014). The application of an unfolding model of the PIRT type to measuremen of attitude. Applied psychological measurement. Vol. 12 pp.33 - 50
Musselwhite, D.J. & Wesolowski, B.C. (2018). standard error of measurement. In Bruce B. Frey (Ed) the SAGE encyclopedia of educational research, measurement and evaluation (pp 1588 – 1590) Thousand Oaks: SAGE publication, Inc.
National Policy on Education, (2013). Federal Republic of Nigeria (2013), National Policy on Education 6th Edition.
Nworgu, B.G, (2015). Educational measurement and evaluation theory and practice (2 Ed). University Trust Publisher.
Obinne, A.D.E. (2012). Using IRT in determining test item prone to guessing. Retrieved march 22nd, 2021, URI: http://dx.doi.org/wje.v2 nIp91.
Obinne, A.D.E. (2018). Test item validity: Item Response Theory (IRT) perspective for Nigeria. Research journal in Organizational Psychology & Educational Studies 2(1). Retrieved April, 30, 2021, from www.emergingresources.org
Otumegwu, T.U., Ezechukwu, I.R., Ojedapo, D.O., (2024). Development of multiple choice test in mathematics using item response theory. Journal of Innovations in Educational Assessment, 6(1), 10-24.
Reeve, B.B. (2000). Item and scale-level analysis of clinical and non-clinical sample responses to the MMP1-2 depression scales employing Item Response Theory. Unpublished doctoral dissertation, University of North Carolina at Chapel Hill.
Ukozor, F.I. (2016). Validity of a test. In Ogomaka, P.M.C, Ekwonye, E.C, Ukozor F.I, and Onah F.E, (Ed) Measurement and evaluation: Acomprehensive text for students and teachers. (pp 218 – 255) Flashpoint Publishers
